Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
-
Updated
Aug 17, 2026 - Python
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Open-source LLM-based ASR model family for Chinese, dialect, accent, and multilingual speech, with FunASR, vLLM, streaming, and llama.cpp runtimes.
Get started using Deepgram's Live Transcription with this Node demo app
Get started using Deepgram's Live Transcription with this Flask demo app
Lightweight real-time ASR powered by a Microsoft offline speech recognition model. CPU-only, supporting 10 languages, Windows, Linux, macOS, and C#, C++, Python SDKs. 基于微软离线语音识别模型的轻量级实时 ASR,纯 CPU 运行,支持 10 种语言及 Windows、Linux、macOS,提供 C#、C++ 和 Python SDK。
Get started using Deepgram's Live Transcription with this Go demo app
Get started using Deepgram's Live STT with this FastAPI demo app
Get started using Deepgram's Live Transcription with this Django demo app
Get started using Deepgram's Live Transcription with this Deno demo app
Get started using Deepgram's Live Transcription with this Ruby demo app
RTGX is an AI-powered real-time glossary explainer that adds contextual subtitles during live lectures. It transcribes speech, identifies complex terms, and provides instant, context-aware definitions using LLM, built for accessibility and multi-language support.
Get started using Deepgram's Live Transcription with this Java demo app
Get started using Deepgram's Live Transcription with this Bun demo app
Get started using Deepgram's Live Transcription with this PHP demo app
Get started using Deepgram's Live Transcription with this C++ demo app
Dictate on Linux with a hotkey, get AI-refined text, and paste it into any focused window.
Get started using Deepgram's Live Transcription with this Rust demo app
Add a description, image, and links to the real-time-asr topic page so that developers can more easily learn about it.
To associate your repository with the real-time-asr topic, visit your repo's landing page and select "manage topics."